Model comparison
GPT-4.1 vs StarCoder 2 3B
GPT-4.1 has enough public results to be ranked (#219); StarCoder 2 3B does not yet, so treat this comparison as directional.
Last verified . 1 shared benchmarks.
NVIDIASummary
- They share 1 benchmark with published results for both. GPT-4.1 scores higher in 1 category and StarCoder 2 3B in 0 categories, but none of those gaps is larger than the uncertainty.
- StarCoder 2 3B has downloadable open weights; the other is API-only.
Side by side
| GPT-4.1 | StarCoder 2 3B | |
|---|---|---|
| Provider | OpenAI | NVIDIA |
| Noometry Index | 35.9 | 36.3 |
| Released | 2025-04-14 | 2024-02-22 |
| Weights | Proprietary | Open |
| Context window | 1.05M | — |
| Max output | 33K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $8 | — |
| Results tracked | 52 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GPT-4.1: 34.4 (#238), StarCoder 2 3B: 33.5
| Benchmark | GPT-4.1 | StarCoder 2 3B |
|---|---|---|
| SWE-bench Verified | 48.5% | — |
| SWE-bench Verified (bash only) | 39.6% | — |
| Aider Polyglot | 52.4% | — |
| WeirdML | 39% | — |
| LMArena Coding | 1391 | — |
| BigCodeBench Complete | — | 21.4% |
| CadEval | 42% | — |
| ALE-Bench | 558.1 | — |
| HumanEval+ | — | 27.4% |
Agentic & Tool Use Not comparable
GPT-4.1: 34.7 (#43), StarCoder 2 3B: —
| Benchmark | GPT-4.1 | StarCoder 2 3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 54% | — |
Reasoning Not comparable
GPT-4.1: 11.7 (#339), StarCoder 2 3B: —
| Benchmark | GPT-4.1 | StarCoder 2 3B |
|---|---|---|
| Epoch Capabilities Index | 136.78 | 88.76 |
| ARC-AGI-2 | 0.4% | — |
| SimpleBench | 27% | — |
| Kagi LLM Benchmark | 52.3% | — |
| ARC-AGI-1 | 5.5% | — |
| Chess Puzzles | 6% | — |
| EnigmaEval | 2.2% | — |
| LMArena Hard Prompts | 1384 | — |
| DTBench | 68.3% | — |
| LMCA | 25.6% | — |
| ForecastBench | 61.5 | — |
| WinoGrande | — | 57.1% |
Math Not comparable
GPT-4.1: 22.3 (#280), StarCoder 2 3B: —
| Benchmark | GPT-4.1 | StarCoder 2 3B |
|---|---|---|
| FrontierMath (Tiers 1-3) | 6% | — |
| OTIS Mock AIME 2024-2025 | 38.3% | — |
| Omni-MATH | 47.1% | — |
| LMArena Math | 1370 | — |
| MATH Level 5 | 83% | — |
| FrontierMath (Feb 2025 set) | 5.5% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
| GSM8K | — | 21.6% |
Knowledge Not comparable
GPT-4.1: 37.1 (#160), StarCoder 2 3B: —
| Benchmark | GPT-4.1 | StarCoder 2 3B |
|---|---|---|
| GPQA Diamond | 66.9% | — |
| Humanity's Last Exam | 5.4% | — |
| SimpleQA Verified | 31.1% | — |
| MMLU-Pro | 81.1% | — |
| Vectara Hallucination Rate | 5.6% | — |
| GPQA (HELM) | 65.9% | — |
| LMArena Expert | 1364 | — |
| ARC (AI2) Challenge | — | 34.2% |
| MMLU | — | 36.6% |
Multimodal Not comparable
GPT-4.1: 38.2 (#67), StarCoder 2 3B: —
| Benchmark | GPT-4.1 | StarCoder 2 3B |
|---|---|---|
| LMArena Vision | 1211 | — |
| GeoBench | 72% | — |
Multilingual Not comparable
GPT-4.1: 49.4 (#133), StarCoder 2 3B: —
| Benchmark | GPT-4.1 | StarCoder 2 3B |
|---|---|---|
| LMArena Non-English | 1370 | — |
| LMArena Chinese | 1382 | — |
| LMArena French | 1382 | — |
| LMArena German | 1381 | — |
| LMArena Japanese | 1319 | — |
| LMArena Korean | 1339 | — |
| LMArena Russian | 1377 | — |
| LMArena Spanish | 1376 | — |
Instruction Following Not comparable
GPT-4.1: 71.3 (#153), StarCoder 2 3B: —
| Benchmark | GPT-4.1 | StarCoder 2 3B |
|---|---|---|
| IFEval | 83.8% | — |
| LMArena Instruction Following | 1367 | — |
Long Context Not comparable
GPT-4.1: 40.0 (#163), StarCoder 2 3B: —
| Benchmark | GPT-4.1 | StarCoder 2 3B |
|---|---|---|
| Fiction.LiveBench | 63.9% | — |
| LMArena Longer Query | 1385 | — |
Writing & Preference Not comparable
GPT-4.1: 57.6 (#125), StarCoder 2 3B: —
| Benchmark | GPT-4.1 | StarCoder 2 3B |
|---|---|---|
| LMArena Text | 1383 | — |
| LMArena Creative Writing | 1363 | — |
| EQ-Bench Creative Writing | 1420 | — |
| WildBench | 85.4% | — |
| LMArena Multi-Turn | 1398 | — |
Frequently asked questions
Is GPT-4.1 better than StarCoder 2 3B?
GPT-4.1 has enough public results to be ranked (#219); StarCoder 2 3B does not yet, so treat this comparison as directional.
Is GPT-4.1 or StarCoder 2 3B better for coding?
They score almost the same on coding (34.4 vs 33.5); test both on your own repository before choosing.
How many benchmarks do GPT-4.1 and StarCoder 2 3B share?
1 benchmark has published results for both models. GPT-4.1 has 52 scored results on Noometry and StarCoder 2 3B has 7.